[Spambayes-checkins] spambayes/contrib findbest.py,1.1,1.2

Skip Montanaro montanaro at users.sourceforge.net
Wed Jan 21 16:44:07 EST 2004


Update of /cvsroot/spambayes/spambayes/contrib
In directory sc8-pr-cvs1:/tmp/cvs-serv22782

Modified Files:
	findbest.py 
Log Message:
wordsmith the doc string a bit.
add a small challenge.


Index: findbest.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/contrib/findbest.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** findbest.py	21 Jan 2004 21:38:49 -0000	1.1
--- findbest.py	21 Jan 2004 21:44:05 -0000	1.2
***************
*** 8,13 ****
  Given a number of unsure messages and a desire to keep your training
  database small, the question naturally arises, "Which message should I add
! to my database next?".  A common approach might be to sort the unsures by
! their SpamBayes scores and train on the one which scores lowest.  That is a
  reasonable approach, but there is no guarantee the lowest scoring unsure is
  in any way related to the other unsure messages.
--- 8,13 ----
  Given a number of unsure messages and a desire to keep your training
  database small, the question naturally arises, "Which message should I add
! to my database next?".  A common approach is to sort the unsures by their
! SpamBayes scores and train on the one which scores lowest.  This is a
  reasonable approach, but there is no guarantee the lowest scoring unsure is
  in any way related to the other unsure messages.
***************
*** 59,62 ****
--- 59,66 ----
      * $HOME/best.pck
  
+ [To do?  Someone might consider the reverse operation.  Given a pile of ham
+ and spam, which message can be removed with the least impact?  What pile of
+ mail should that removal be tested against?]
+ 
  '''
  





More information about the Spambayes-checkins mailing list